Search

Your search keyword '"Dubljevic, Stevan"' showing total 70 results
Start Over Author "Dubljevic, Stevan" Publisher ieee
70 results on '"Dubljevic, Stevan"'

4. Transfer Learning for Dynamic Feature Extraction Using Variational Bayesian Inference.

Author

Xie, Junyao, Huang, Biao, and Dubljevic, Stevan

Subjects
BAYESIAN field theory, FIX-point estimation, MANUFACTURING processes, DISTRIBUTION (Probability theory), ONLINE education
Abstract

Data-driven methods have been extensively utilized in establishing predictive models from historical data for process monitoring and prediction of quality variables. However, most data-driven approaches assume that training data and testing data come from steady-state operating regions and follow the same distribution, which may not be the case when it comes to complex industrial processes. To avoid these restrictive assumptions and account for practical implementation, a novel online transfer learning technique is proposed to dynamically learn cross-domain features based on the variational Bayesian inference in this work. Stemming from the probabilistic slow feature analysis, a transfer slow feature analysis (TSFA) technique is presented to transfer dynamic models learned from different source processes to enhance prediction performance in the target process. In particular, two weighting functions associated with transition and emission equations are introduced and updated dynamically to quantify the transferability from source domains to the target domain at each time instant. Instead of point estimation, a variational Bayesian inference scheme is designed to learn the parameters under probability distributions accounting for corresponding uncertainties. The effectiveness of the proposed technique with applications to soft sensor modelling is demonstrated by a simulation example, a public dataset and an industrial case study. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

14. Robust State Estimation for Positive Real Infinite-Dimensional Systems With Actuator and Sensor Faults.

Author

Xu, Xiaodong and Dubljevic, Stevan

Abstract

In this article, we propose a novel framework on the state estimation for a class of positive real infinite-dimensional systems, which suffer from unknown actuator and sensor faults and uncertain exogenous disturbance. Four cases of fault occurrence are taken into account: single multiplicative actuator fault, single multiplicative sensor fault, simultaneous actuator and sensor faults, and single actuator fault with a dead-zone nonlinearity. We develop new adaptive laws for the estimation of fault parameters and embed the proposed laws into the infinite dimensional state observer design. Moreover, by considering the actuator fault with a dead-zone nonlinearity, an infinite dimensional observer associated with coupled parameter update laws is developed to help to complete the fault accommodation. This is achieved by reconfiguring the actuator input based on the estimated information of parameters in the actuator fault map with a dead-zone nonlinearity. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results